image-ocr-hardened
Fail
Audited by Snyk on Apr 21, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to display OCR output to the terminal and to warn/identify credential-containing text, which requires the model to emit any extracted secret values verbatim (creating exfiltration risk).
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata